Menu

Part 3: Bounded AST CallLedger & Trace Diffing CLI in SpaghettiLens-AI (v0.6.0)
📰

Part 3: Bounded AST CallLedger & Trace Diffing CLI in SpaghettiLens-AI (v0.6.0)

DEV Community: machinelearning·Giuseppe Dario Camiolo·about 6 hours ago
#MXOr0737
Long article (939 words) — no AI summary yet.
Reading 0:00
15s threshold

In Part 1 and Part 2 , I used a 4B model ( qwen3-4b-instruct-2507 ) inside a 4,096-token sliding window on a local Snapdragon NPU as an exploratory wind tunnel for a 3-tier smolagents hierarchy ( L0 Supervisor $\rightarrow$ L1 Team Leads $\rightarrow$ L2 Specialists ). As noted in Part 2, these runs are exploratory diagnostics rather than a controlled benchmark proving model parity.

SpaghettiLens-AI v0.6.0 ( GitHub repository ) adds two practical controls for this setup:

Out-of-Window CallLedger & Duplicate Static Call Guard ( core/call_ledger.py , core/smol_hierarchy.py )

Same-Input Trace Diffing CLI ( core/trace_diff.py , cli/bench.py )

1. Catching Repeated Static Calls Under a Sliding Context Window

When multi-step ActionStep history rolls past a 4,096-token window, a compact model can re-emit a tool or sub-agent call it already ran earlier in the session.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.